Duet is a second, larger agent that automates all auxiliary tasks—writing procedures, tests, and monitoring—required to support the primary conversational agent.
Decagon launched Duet, a slower but more capable agent that handles procedure writing, integration, testing, and conversation monitoring, replacing manual auxiliary work. ✦ AI generated
Jesse · a16z Podcast · 2026-07-31 · original ↗
starts at this moment · 30:50
“Can you make that concrete for us? Like what are some of the oh moments as you improve your product for your customer...”
And so what duet is is it's kind of a separate agent. It's like a second agent that's much bigger, much slower, but its job is to do all the tasks I just described. So now instead of us having to write these AOPs and write these integrations and tools into their systems and write these tests and monitor the conversations, do just does all of that, right? So it's like a it's a second agent that is smart enough to do all these things and um it it just feels very magical because you can just literally tell it like hey I've nothing built yet so far, but here's a bunch of transcripts I have and here's some documentation. like you go figure out the best way to like do these all these procedures I want and it'll go do it and then of its own accord it'll also write the tests and simulations that go along with those.
verbatim transcript · starts at 30:50
30:50our own format of procedures we call them agent operating procedures that teach the AI how to do things we had to write these tools that the procedures can use to access systems and pull APIs and whatever and then after that we need to like create all these tests to make sure that this thing is working well and that you can kind of simulate all these different sit situations and afterwards
31:09once they're in production like we would manually be reading conversations, right? There's like a ton of work that goes into it even though the core product we're building is is itself an agent. And so what duet is is it's kind of a separate agent. It's like a second agent that's much bigger, much slower, but its job is to do all the tasks I just described. So now instead of us
31:27having to write these AOPs and write these integrations and tools into their systems and write these tests and monitor the conversations, do just does all of that, right? So it's like a it's a second agent that is smart enough to do all these things and um it's it just feels very magical because you can just literally tell it like hey I've nothing built yet so far, but here's a bunch of
31:50transcripts I have and here's some documentation. like you go figure out the best way to like do these all these procedures I want >> and it'll go do it and then of its own accord it'll also write the tests and simulations that go along with those and once you're done with that and you actually put in front of customers it'll be the one that's monitoring all the
32:08conversations and it'll flag things where things are going well or poorly and it'll say like yeah I read you know these thousand conversations and actually there's this one topic that we do really poorly on >> and I've noticed that and I've also drafted these improvements for you so it's like >> wow It's like one agent that can do all of that. And so that that's very magical
32:26because well first of all it was not possible when we first started the company. It only became possible when all the reasoning models got better and of course anthropic open are making these reasoning models mostly for like the cloud codes of the world but they are also really good for like duet for example and that was kind of like a moment where it's like oh wow like first